End of training

README.md

@@ -4,18 +4,18 @@ base_model: facebook/bart-base
 tags:
 - generated_from_trainer
 model-index:
-- name: bart-with-asr-noise-ins-0.4
+- name: bart-with-asr-noise-ins-0.5
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# bart-with-asr-noise-ins-0.4
+# bart-with-asr-noise-ins-0.5
 
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0541
+- Loss: 0.0595
 
 ## Model description
 
@@ -47,10 +47,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.1609        | 0.62  | 500  | 0.0887          |
-| 0.0935        | 1.24  | 1000 | 0.0645          |
-| 0.0532        | 1.86  | 1500 | 0.0592          |
-| 0.0267        | 2.48  | 2000 | 0.0541          |
+| 0.1471        | 0.62  | 500  | 0.0876          |
+| 0.1012        | 1.24  | 1000 | 0.0708          |
+| 0.0474        | 1.86  | 1500 | 0.0607          |
+| 0.0257        | 2.48  | 2000 | 0.0595          |
 
 
 ### Framework versions